LLM Dependency Parsing with In-Context Rules

We study whether incorporating symbolic rules can aid large language models in dependency parsing.We consider a paradigm in which LLMs first produce symbolic rules given fully labeled examples, and the rules are then provided in a subsequent call that performs the actual parsing.In addition, we experiment with providing human-created annotation guidelines in-context to the LLMs.We find that while both methods for rule incorporation improve zero-shot performance, the benefit disappears with a few labeled in-context examples.